Abstract: A technique for detecting an environmental change to a delivery zone via an unmanned aerial vehicle includes obtaining an anchor image and an evaluation image, each representative of the delivery zone, providing the anchor image and the evaluation image to a machine learning model to determine an embedding score associated with a distance between representations of the anchor image and the evaluation image within an embedding space, and determining an occurrence of the environmental change to the delivery zone when the embedding score is greater than a threshold value.

Abstract: A system and method are provided. The method comprises obtaining a camera live stream from a camera in a user device, the camera live stream including image data of a particular product; determining one or more image features common to images of one or more products based at least on image analysis of image data of the images of the one or more products; comparing the one or more image features to one or more image features of the image data of the particular product to generate one or more potential adjustments to the one or more image features of the image data of the particular product; and providing, for presentation together with the camera live stream on the user device, at least one indication based on the one or more potential adjustments to the one or more image features of the image data of the particular product.

Abstract: Systems and methods for detecting blockages in images are described. An example method may include receiving a plurality of images captured by a camera installed on an apparatus. The method may include identifying one or more candidate blocked regions in the plurality of images. Each of the candidate blocked regions may contain image data caused by blockages in the camera's field-of-view. The method may further include assigning scores to the one or more candidate blocked regions based on relationships among the one or more candidate blocked regions in the plurality of images. In response to a determination that one of the scores is above a predetermined blockage threshold, the method may include generating an alarm signal for the apparatus.

Abstract: A feature mapping computer system configured to (i) receive a localized image including a photo depicting a driving environment and location data associated with the photo, (ii) identify, using an image recognition module, a roadway feature depicted in the photo, (iii) generate, using a photogrammetry module, a point cloud based upon the photo and the location data, wherein the point cloud comprises a set of data points representing the driving environment in a three dimensional (“3D”) space, (iv) localize the point cloud by assigning a location to the point cloud based upon the location data, and (v) generate an enhanced base map that includes a roadway feature.

Abstract: An apparatus for displaying a moving region of interest located within a body includes a positioning system to determine a position and orientation (P&O) of a medical device as well as to track, using an internal position reference sensor, the motion of the region of interest over time. A compensation function block generates a motion compensation function based on the motion of the region of interest, which is configured to compensate for the motion of the region of interest between a first time, for example a time at which an image was acquired and a second time, for example a time at which a P&O of the device was measured. The measured P&O is corrected using the compensation function. A representation of the medical device is superimposed on the image in accordance with the corrected P&O.

Abstract: A method of processing a series of images of an embryo to determine estimated timings of developmental events for the embryo, wherein the method comprises: determining feature information for each image, the feature information for each image representing the content of the image; establishing machine learned classifiers for associating each image with a respective likelihood of the image being associated with one or more developmental events based on the feature information for the image; applying the machine learned classifiers to the feature information for each image to determine a respective likelihood of the image being associated with one or more developmental events, and determining estimated timings for the plurality of developmental events for the embryo from the respective likelihoods of the respective images being associated with respective ones of the plurality of developmental events. The method may further comprise determining an indication of a confidence estimate for the timings.

Abstract: A computer-implemented method according to one embodiment includes running an initial network on a plurality of images to detect actors pictured therein and body joints of the detected actors. The method further includes running fully-connected networks in parallel, one fully-connected network for each of the detected actors, to reconstruct complete three-dimensional poses of the actors. Sequential model fitting is performed on the plurality of images. The sequential model fitting is based on results of running the initial network and the fully-connected networks. The method further includes determining, based on the sequential model fitting, a locational position for a camera in which the camera has a view of a possible point of collision of two or more of the actors. The camera is instructed to be positioned in the locational position.

Abstract: Autonomous driving system methods and devices which trigger vehicular actions based on the monitoring of one or more occupants of a vehicle are presented. The methods, and corresponding devices, may include identifying a plurality of features in a plurality of subsets of image data detailing the one or more occupants; tracking changes over time of the plurality of features over the plurality of subsets of image data; determining a state, from a plurality of states, of the one or more occupants based on the tracked changes; and triggering the vehicular action based on the determined state.

Abstract: A system for measuring dimensions of film to be applied to a window includes a plurality of removable cards for placement on the window, each of the plurality of removable cards having a plurality of visible correspondence points at pre-defined positions on the respective removable card. The system further includes a mobile device having an image capture device, and the image capture device is configured to capture an image of the window having a set of correspondence points visible in the image. Additionally, the system includes a server configured to receive the image of the window captured by the mobile device and process the image to determine dimensions of a film to be cut for the window based on the set of correspondence points and the pre-defined positions, and processing the image removes perspective distortions in the image. The system is configured to output the dimensions of the film.

Abstract: A system and method for identifying abnormal medical images. The system can be configured to receive a medical image, segment an anatomical structure from the medical image to define a segmented dataset, register the segmented dataset to a baseline dataset defining a normal anatomical structure, classify, by an abnormality classifier, whether the anatomical structure within the medical image as either abnormal or normal, wherein the abnormality classifier comprises a machine learning algorithm trained to distinguish between normal and abnormal versions of the anatomical structure in medical images, and based on whether the anatomical structure can be segmented from the medical image, whether the segmented dataset can be registered to the baseline dataset, or a classification associated with the medical image output by the abnormality classifier, flagging the medical image as either normal or abnormal.

Abstract: Techniques related to object detection using an adaptive convolutional neural network (CNN) are discussed. Such techniques include applying one of multiple configurations of the CNN to input image data in response to an available computational resources for processing the input image data.

Abstract: This disclosure is directed to using cascading algorithms to automatically identify items placed in a tote or other receptacle utilized by users in material handling facilities as the users move around the facilities. A tote may store a database or “gallery” of item representations for all of the items that are stored in the facility that a user may place in their totes. The tote may use multiple algorithms in a cascading manner to analyze the gallery of item representations in order to iteratively narrow the search space of item representations in the gallery to determine which of the items was placed in the tote by a user. Upon identifying the item placed in the tote, the tote may add an item identifier for the item to a virtual listing of item identifiers representing items previously placed in the tote.

Abstract: A system or method for an imaging system is provided for inspecting a heliostat. The imaging system includes a platform and a camera mounted on the platform and a heliostat having a plurality of mirrored facets. The camera is positioned to acquire a first image that serves as a reference image and a second image that is a reflected image from at least one facet. The camera stores image data associated with the first image and the second image, and wirelessly transmits the stored image data to a computing apparatus. The computing apparatus compares the first image with the second image and determines a performance parameter associated with the heliostat.

Abstract: A method for detecting road diseases by intelligent cruise via an unmanned aerial vehicle (UAV), the UAV and a detecting system therefor are provided. The method for detecting road diseases by intelligent cruise via UAV, wherein a road disease detection model and a road recognition model based on deep learning network are built in the UAV, wherein the method specifically comprises a step of: automatically flying the UAV on a predetermined route on the actual road determined by the road recognition model, and obtaining road disease test results by the road surface disease detection model. The present invention adopts the road recognition model and road disease detection model based on deep learning network, which can realize automatic cruise and automatic road disease detection, only need to set a predetermined route or area range, which is convenient and fast.

Abstract: An apparatus for identifying the state of a signal light includes a processor configured to input time series images into a first classifier to detect object regions each including a vehicle equipped with a signal light in the respective images, the first classifier having been trained to detect the vehicle; chronologically input characteristics obtained from pixel values of the object regions detected in the respective images into a second classifier to calculate confidence scores of possible candidate states of the signal light of the vehicle, the second classifier having a recursive structure or performing a convolution operation in a temporal direction; and identify the state of the signal light, based on the preceding state of the signal light, information indicating whether transitions between the candidate states of the signal light are allowed, and the confidence scores of the respective candidate states.

Abstract: Embodiments of this application disclose an object annotation method and apparatus, a movement control method and apparatus, a device, and a storage medium. The method includes: obtaining a reference image recorded by an image sensor from an environment space, the reference image comprising at least one reference object; obtaining target point cloud data obtained by a three-dimensional space sensor by scanning the environment space, the target point cloud data indicating a three-dimensional space region occupied by a target object in the environment space; determining a target reference object corresponding to the target object from the reference image; determining a projection size of the three-dimensional space region corresponding to the target point cloud data and the three-dimensional space region being projected onto the reference image; and performing three-dimensional annotation on the target reference object in the reference image according to the determined projection size.

Abstract: The present disclosure provides an object pose obtaining method, and an electronic device, relates to technology fields of image processing, computer vision, and deep learning. A detailed implementation is: extracting an image block of an object from an image, and generating a local coordinate system corresponding to the image block; obtaining 2D projection key points in an image coordinate system corresponding to a plurality of 3D key points on a 3D model of the object; converting the 2D projection key points into the local coordinate system to generate corresponding 2D prediction key points; obtaining direction vectors between each pixel point in the image block and each 2D prediction key point, and obtaining a 2D target key point corresponding to each 2D predication key point based on the direction vectors; and determining a pose of the object according to the 3D key points and the 2D target key points.

Abstract: A system and method for image recognition registration of a person into an event. The person is registered in the event using image recognition technology. A digital image of the person taken by a camera is compared with a stored profile image of the person to identify the person and enter them into the event without the need for the person to pre-register for the particular event. Enhanced recognition techniques incorporating pattern recognition may be used to increase identity accuracy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining that current data captured at a current location of a drone satisfies localization adjustment criteria; in response to determining that the current data captured at the current location of the drone satisfies the localization adjustment criteria, identifying previously captured image data; determining a previous expected location of the drone based on both an expected change in location of the drone and a first previous location determined from other image data captured before the previously captured image data; determining a location difference between the previous expected location of the drone and a second previous location determined from the previously captured image data; and determining the current location of the drone based on the location difference.

Abstract: Systems and methods for driving a flexible medical instrument to a target in an anatomical space with robotic assistance are described herein. The flexible instrument may have a tracking sensor embedded therein. An associated robotic control system may be provided, which is configured to register the flexible instrument to an anatomical image using data from the tracking sensor and identify one or more movements suitable for navigating the instrument towards an identified target. In some embodiments, the robotic control system drives or assists in driving the flexible instrument to the target.